Speaker
Description
Ptychographic imaging generates high-resolution datasets at the cost of heavy computational complexity, limiting its use in real-time experimental decision-making. In this cross-institutional effort, we introduce a hybrid edge-to-cloud workflow that delivers fast feedback for ptychography experiments by combining a modern synchrotron beamline at Diamond Light Source I13-1, featuring an upgraded motion control system for rapid probe scanning, with a high-speed detector (DECTRIS SELUN), a GPU-accelerated edge processing pipeline, and DECTRIS CLOUD services.
Our approach integrates on-prem edge computing for immediate reconstruction previews or anomaly detection with cloud-based processing pipelines for full-resolution analysis. This will enable scientists to monitor sample quality and adapt acquisition parameters within seconds to minutes, aiming to improve experimental efficiency and data quality.
This framework was prototyped during a joint hackathon and demonstrated during initial measurements at Diamond Light Source (Beamline I13-1). It pivots how scientific experiments can benefit from near real-time feedback and enables the integration of modern ML workflows, edge computing, and scalable cloud infrastructure. We discuss our architectural design and outline future steps toward deployable real-time feedback systems that pave the way towards autonomous exploration in materials science and X-ray imaging.